Web site classification based on URL and content: Algerian vs. non-Algerian case

Abstract

Web page classification based on topic or sentiments is a common application of web content mining techniques. In this paper we will present a novel application intended to identify the nation targeted by a specific web page. The aim is to be able to automatically distinguish websites targeting a specific nation, using both the URL and the content of a web page. In this paper we will address the issue of identifying Algerian-interest web pages using a machine learning approach. We will present the process of acquiring data for the supervised learning phase and adapting it into a usable dataset, as well as using it to construct three distinct classifiers using different parts of the data. The resulting classifiers have shown outstanding performances (up to F-score = 0.93) for such application.